Michiel Bacchiani

Publication List Details

Period

2000 - 2007

Number

19

Co-Authors

Speech Recognition Based On Acoustically Derived Segment Units (2007)

Toshiaki Fukada, Michiel Bacchiani, Kuldip K. Paliwal, Yoshinori Sagisaka

This paper describes a new method of word model generation based on acoustically derived segment units (henceforth ASUs). An ASU-based approach has the advantages of growing out of human...

1 (2007)

Aaron Rosenberg, Julia Hirschberg, Michiel Bacchiani, S Parthasarathy, Philip Isenhour, Larry Stead

SCANMail is a prototype system developed at AT&T Labs for the purpose of providing useful tools for managing and searching through voicemail messages. Content is extracted from voicemail messages...

4 (2007)

Julia Hirschberg, Michiel Bacchiani, Don Hindle, Phil Isenhour, Aaron Rosenberg, Litza Stark, ...

Increasing amounts of public, corporate, and private audio data are available for use, but limited in usefulness by the lack of tools to permit their browsing and search. In this paper, we describe...

yyy (2007)

Toshiaki Fukada, Michiel Bacchiani, Kuldip K. Paliwal, Yoshinori Sagisaka

This paper describes a new method of word model generation based on acoustically derived segment units (henceforth ASUs). An ASU-based approach has the advantages of growing out of human...

Improved Name-Recognition with Meta-data dependent name networks (2004)

Sameer R. Maskey, Michiel Bacchiani, Brian Roark, Richard Sproat

A transcription system that requires accurate general name transcription is faced with the problem of covering the large number of names it may encounter. Without any prior knowledge, this requires a...

Language model adaptation with MAP estimation and the perceptron algorithm (2004)

Michiel Bacchiani, Brian Roark, Murat Saraclar

In this paper, we contrast two language model adaptation approaches: MAP estimation and the perceptron algorithm. Used in isolation, we show that MAP estimation outperforms the latter approach, for...

Scanmail: a voicemail interface that makes speech browsable, readable and searchable (2002)

Steve Whittaker, Julia Hirschberg, Brian Amento, Litza Stark, Michiel Bacchiani, Philip Isenhour, ...

Increasing amounts of public, corporate, and private speech data are now available on-line. These are limited in their usefulness, however, by the lack of tools to permit their browsing and search....

Scanmail: a voicemail interface that makes speech browsable, readable and searchable (2002)

Steve Whittaker, Julia Hirschberg, Brian Amento, Litza Stark, Michiel Bacchiani, Phil Isenhour, ...

Increasing amounts of public, corporate, and private speech data are now available on-line. These are limited in their usefulness, however, by the lack of tools to permit their browsing and search....

SCANMail: a voicemail interface that makes speech browsable, readable and searchable (2002)

Steve Whittaker, Julia Hirschberg, Brian Amento, Litza Stark, Michiel Bacchiani, Philip Isenhour, ...

Increasing amounts of public, corporate, and private speech data are now available on-line. These are limited in their usefulness, however, by the lack of tools to permit their browsing and search....

Automatic transcription of voicemail at AT&T (2001)

Michiel Bacchiani

This paper reports on the automatic transcription accuracy of voicemail messages. It shows that vocal tract length normalization and adaptation using linear transformations, proven to improve...

SCANMail: Browsing and searching speech data by content (2001)

Julia Hirschberg, Michiel Bacchiani, Don Hindle, Phil Isenhour, Aaron Rosenberg, Litza Stark, ...

Increasing amounts of public, corporate, and private audio data are available for use, but limited in usefulness by the lack of tools to permit their browsing and search. In this paper, we describe...

Automatic Transcription Of Voicemail At Att (2001)

Michiel Bacchiani Att, Michiel Bacchiani

This paper reports on the automatic transcription accuracy of voicemail messages. It shows that vocal tract length normalization and adaptation using linear transformations, proven to improve...

SCANMail: Audio navigation in the voicemail domain (2000)

Michiel Bacchiani, Julia Hirschberg, Aaron Rosenberg, Steve Whittaker, Donald Hindle, Phil Isenhour, ...

This paper describes SCANMail, a system that allows users to browse and search their voicemail messages by content through a GUI. Content based navigation is realized by use of automatic speech...

Using Maximum Likelihood Linear Regression for Segment Clustering and Speaker Identification (2000)

Michiel Bacchiani

Many adaptation scenarios rely on clustering of either the test or training data. Although consistency between the clustering and adaptation objective functions is desired, most previous approaches...

SCANMail: Audio navigation in the voicemail domain (2000)

Michiel Bacchiani, Julia Hirschberg, Aaron Rosenberg, Steve Whittaker, Donald Hindle, Phil Isenhour, ...

This paper describes SCANMail, a system that allows users to browse and search their voicemail messages by content through a GUI. Content based navigation is realized by use of automatic speech...

SCANMail: Audio navigation in the voicemail domain (2000)

Michiel Bacchiani, Julia Hirschberg, Aaron Rosenberg, Steve Whittaker, Donald Hindle, Phil Isenhour, ...

Increasing amounts of public, corporate, and private audio present a major challenge to speech, information retrieval, and human-computer interaction research: how can we help people to take...

AT&T at TREC-8 (2000)

Amit Singhal, Steve Abney, Michiel Bacchiani, Michael Collins, Donald Hindle, O Pereira

In 1999, AT&T participated in the ad-hoc task and the Question Answering (QA), Spoken Document Retrieval (SDR), and Web tracks. Most of our effort for TREC-8 focused on the QA and SDR tracks....

AT&T at TREC-8 (2000)

Amit Singhal, Steve Abney, Michiel Bacchiani, Michael Collins, Donald Hindle, O Pereira

In 1999, AT&T participated in the ad-hoc task and the Question Answering (QA), Spoken Document Retrieval (SDR), and Web tracks. Most of our e ort for TREC-8 focused on the QA and SDR tracks....

SCANMail: Browsing and Searching Speech Data by Content

Julia Hirschberg Michiel, Michiel Bacchiani, Don Hindle, Phil Isenhour, Aaron Rosenberg, Litza Stark, ...

Increasing amounts of public, corporate, and private audio data are available for use, but limited in usefulness by the lack of tools to permit their browsing and search. In this paper, we describe...